Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Psychological
    -0.65
    sa
    -0.64
     Reincarnated
    -0.63
    >]
    -0.60
    ainted
    -0.60
     IPM
    -0.59
     palms
    -0.59
     Maced
    -0.58
    eting
    -0.58
    BIL
    -0.58
    POSITIVE LOGITS
    oday
    0.77
    haus
    0.77
    ycle
    0.67
     Baal
    0.66
    iations
    0.65
    gradation
    0.64
     relativity
    0.64
    ertodd
    0.64
    oster
    0.63
     blockers
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.